- Unlock your edge with PFF+: Access Premium Stats, dominate fantasy with in-season tools and projections and make smarter bets with the new PFF Player Prop Tool. Get 25% off your PFF+ annual subscription with code PFFFANTASYPODCAST25.
Estimated Reading Time: 4 minutes
Last year, I introduced a new framework for understanding wide receiver play, quarterback decision-making and offensive potential. This framework relies on an XGBOOST model and PFF’s impressive collection of route-level data. Using machine learning and this breadth of PFF data, we can create models with the goal of predicting where a target should go on a given play.
The resulting metrics, Share of Predicted Targets and Share of Predicted Air Yards, are both more stable than their “actual” counterparts.
Week 7 Recap
- Cooper Kupp: 1 target – 3.45% target share
- Tucker Kraft: 10 targets – 35.71% target share
- Isaiah Bond: 1 target (the Browns only attempted 18 passes in a rough weather game)
Potential Breakouts: Week 8
These are players who were open significantly more than they garnered targets in Week 7. In general, players who show up on this list see an uptick in targets per route run and target share relative to both themselves and all players with similar target shares.
Scripted Share of Predicted Targets
One advantage of the Predicted Targets Model is that we can create splits on any plays where a player is on the field, whether they actually earn a target or not. One way we can do this is by looking at how teams are deploying players in the first 15 plays of a game, where most coaches are scripting plays.
As we have previously discussed, Share of Predicted Targets (SPT) has a superior stability and predictiveness to actual target share. This is what allows the breakout model to function. This holds true for scripted plays (the first 15 plays of the game)
Scripted SPT is roughly three times more stable than traditional target share and 33% more predictive. We discussed this in the second article of “Coach, I Was Open.” But over the entire game, SPT is incredibly stable and predictive, as seen in the table above.
I wanted to investigate which players to which teams were scripting predicted targets, and who was missing out on those first opportunities. These are potentially players to look at getting some early targets in upcoming games.
D.K. Metcalf is our headliner for breakouts this week, and has a massive scripted SPT deficit. I would expect him to receive plenty of early targets on Sunday Night Football this week against the Packers.
Chigoziem Okonkwo plays the Colts this week, who allow the most targets to tight ends — and, according to PFF Key Insights, permit the second-highest yards per route run to tight ends.
Week 7 “Coach, I Was Open” Review
Let’s start by investigating Chimere Dike in last week’s matchup. This is one of the first plays of the game against a Cover 1 look from New England. Both Elic Ayomanor and Dike get open on this play, and both have a very respectable probability of earning a target (54% and 43%, respectively).
Although Ayomanor’s probability of a target is higher here, I believe Dike would have been the better choice. Ayomanor’s defender ends up falling as the pass is thrown, causing an explosive play of 20 yards. Had the defender not fallen, this is most likely a gain of fewer than eight yards. On the other hand, Dike earned massive separation 15-plus yards from the line of scrimmage and possibly could have scored with a well-placed ball.
Next, let's look at Lil’Jordan Humphrey.
Second-and-10 with eight minutes left in the first quarter. Jaxson Dart drops back to pass and immediately feels pressure, even with all defenders blocked properly. Dart begins to scramble within the mostly clean pocket.
Lil’Jordan Humphrey breaks through the Broncos’ Cover 6 defense into a wide-open single-coverage situation (56% target probability). He has multiple steps on the defender and probably scores a touchdown with a well-placed ball. Dart uses his excellent scrambling ability to extend the play and make what ends up being an incredible throw and catch to Wan’Dale Robinson for 23 yards.
This is an example of a young quarterback making the game slightly harder on himself by not trusting in his protection enough to scan the field and find a wide open explosive play (or possible touchdown).
© 2026 PFF - all rights reserved.